Vibe Coding DiscoverF5-TTS
View on GitHubOfficial code for "F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching"
Python implementation of F5-TTS and E2 TTS for text-to-speech generation, including reference-audio voice cloning, CLI and Gradio interfaces, and training or fine-tuning workflows.
Use Cases
Generate speech from textClone a voice from reference audioCreate multi-speaker or multi-style speechFine-tune a speech-generation modelBuild a local text-to-speech service
Built With
- Language
- Python
- Frameworks
- PyTorch · Gradio · Hugging Face Accelerate · Transformers · torchdiffeq · Vocos · TensorRT-LLM
Tags
text-to-speech · speech-generation · voice-cloning · flow-matching · audio · multilingual · inference · fine-tuning